[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-teams-reply-drafting":3,"mdc--piwivs-key":36,"related-org-openai-teams-reply-drafting":492,"related-repo-openai-teams-reply-drafting":697},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"teams-reply-drafting","draft replies for Microsoft Teams messages","Draft Microsoft Teams replies from available context. Use when the user wants help finding messages that likely need a response and preparing reply drafts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Productivity","productivity","tag",{"name":17,"slug":18,"type":15},"Writing","writing",{"name":20,"slug":21,"type":15},"Microsoft Teams","microsoft-teams",{"name":23,"slug":24,"type":15},"Communications","communications",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-06T18:41:31.450149",null,465,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fteams\u002Fskills\u002Fteams-reply-drafting","---\nname: teams-reply-drafting\ndescription: Draft Microsoft Teams replies from available context. Use when the user wants help finding messages that likely need a response and preparing reply drafts.\n---\n\n# Teams Reply Drafting\n\nUse this skill to identify Teams messages that likely need a reply and produce draft responses grounded in the available conversation context.\n\n## Related Skills\n\n| Workflow | Skill |\n| --- | --- |\n| Refine or send the final Teams text | [..\u002Fteams-messages\u002FSKILL.md](..\u002Fteams-messages\u002FSKILL.md) |\n| Create Microsoft Planner tasks instead of replying in Teams | [..\u002Fteams-planner-task-management\u002FSKILL.md](..\u002Fteams-planner-task-management\u002FSKILL.md) |\n\n## Start Here\n\n- If the user provided channels, threads, chats, people, or a time window, use that scope instead of the default fallback.\n- If no source scope was provided, treat this as best-effort reply drafting from available Teams signals rather than an exact \"messages needing reply\" detector.\n- Use draft replies when the user asked for drafting or review, and send when the requested action is to post or reply now.\n\n## Workflow\n\n1. If the user gave explicit scope, use the cheapest matching path first:\n   - specific message or thread path: `fetch`, then `reply_to_message` only if the user wants to send\n   - named channel: `resolve_team`, `resolve_channel`, then `list_channel_messages`\n   - named chat or DM: `resolve_chat`, then `list_chat_messages`\n2. If no explicit scope was provided, start with:\n   - `list_chats(unread_only=True)` for unread direct conversations and group chats\n   - `list_recent_threads` for recent channel or chat activity\n3. Expand only the conversations needed to answer accurately:\n   - unread chats first\n   - then recent messages containing direct questions or clear asks\n   - then recent mentions detected from message-history reads\n4. To detect recent mentions, get the caller profile and match `TeamsMessageResult.mentions` against the caller's user ID from direct message-history reads. Do not rely on Teams search hits for mention detection.\n5. If the context is incomplete, write the smallest useful clarifying reply instead of guessing.\n6. If a message contains a follow-up but no reply is needed, say that directly. If the user wants it tracked, route the follow-up to the Planner skill instead of drafting a performative Teams reply.\n\n## Drafting Rules\n\n- Answer the question first, then add clarification or next steps only when the context supports it.\n- Keep in-thread replies short unless the thread clearly requires a longer answer.\n- Preserve thread-specific facts, dates, links, and owners.\n- If there are multiple plausible reply targets, stop and ask which conversation the user means before drafting anything send-ready.\n\n## Formatting\n\nFormat multiple drafts as:\n\n```md\n*Teams Reply Drafts — \u003Cscope>*\n\n*\u003Cchat \u002F channel \u002F thread info>*\nDraft:\n\u003Cdraft text>\n\n*\u003Cchat \u002F channel \u002F thread info>*\nDraft:\n\u003Cdraft text>\n```\n\n- Keep each item minimal: a short header plus the draft text.\n- If the user asked for a single reply, return only that item.\n- If nothing likely needing a reply is found, say so directly and explain the scope checked.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,55,62,123,129,149,154,308,314,337,343,348,468,486],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Teams Reply Drafting",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53],{"type":47,"value":54},"Use this skill to identify Teams messages that likely need a reply and produce draft responses grounded in the available conversation context.",{"type":42,"tag":56,"props":57,"children":59},"h2",{"id":58},"related-skills",[60],{"type":47,"value":61},"Related Skills",{"type":42,"tag":63,"props":64,"children":65},"table",{},[66,85],{"type":42,"tag":67,"props":68,"children":69},"thead",{},[70],{"type":42,"tag":71,"props":72,"children":73},"tr",{},[74,80],{"type":42,"tag":75,"props":76,"children":77},"th",{},[78],{"type":47,"value":79},"Workflow",{"type":42,"tag":75,"props":81,"children":82},{},[83],{"type":47,"value":84},"Skill",{"type":42,"tag":86,"props":87,"children":88},"tbody",{},[89,107],{"type":42,"tag":71,"props":90,"children":91},{},[92,98],{"type":42,"tag":93,"props":94,"children":95},"td",{},[96],{"type":47,"value":97},"Refine or send the final Teams text",{"type":42,"tag":93,"props":99,"children":100},{},[101],{"type":42,"tag":102,"props":103,"children":105},"a",{"href":104},"..\u002Fteams-messages\u002FSKILL.md",[106],{"type":47,"value":104},{"type":42,"tag":71,"props":108,"children":109},{},[110,115],{"type":42,"tag":93,"props":111,"children":112},{},[113],{"type":47,"value":114},"Create Microsoft Planner tasks instead of replying in Teams",{"type":42,"tag":93,"props":116,"children":117},{},[118],{"type":42,"tag":102,"props":119,"children":121},{"href":120},"..\u002Fteams-planner-task-management\u002FSKILL.md",[122],{"type":47,"value":120},{"type":42,"tag":56,"props":124,"children":126},{"id":125},"start-here",[127],{"type":47,"value":128},"Start Here",{"type":42,"tag":130,"props":131,"children":132},"ul",{},[133,139,144],{"type":42,"tag":134,"props":135,"children":136},"li",{},[137],{"type":47,"value":138},"If the user provided channels, threads, chats, people, or a time window, use that scope instead of the default fallback.",{"type":42,"tag":134,"props":140,"children":141},{},[142],{"type":47,"value":143},"If no source scope was provided, treat this as best-effort reply drafting from available Teams signals rather than an exact \"messages needing reply\" detector.",{"type":42,"tag":134,"props":145,"children":146},{},[147],{"type":47,"value":148},"Use draft replies when the user asked for drafting or review, and send when the requested action is to post or reply now.",{"type":42,"tag":56,"props":150,"children":152},{"id":151},"workflow",[153],{"type":47,"value":79},{"type":42,"tag":155,"props":156,"children":157},"ol",{},[158,232,262,285,298,303],{"type":42,"tag":134,"props":159,"children":160},{},[161,163],{"type":47,"value":162},"If the user gave explicit scope, use the cheapest matching path first:\n",{"type":42,"tag":130,"props":164,"children":165},{},[166,188,214],{"type":42,"tag":134,"props":167,"children":168},{},[169,171,178,180,186],{"type":47,"value":170},"specific message or thread path: ",{"type":42,"tag":172,"props":173,"children":175},"code",{"className":174},[],[176],{"type":47,"value":177},"fetch",{"type":47,"value":179},", then ",{"type":42,"tag":172,"props":181,"children":183},{"className":182},[],[184],{"type":47,"value":185},"reply_to_message",{"type":47,"value":187}," only if the user wants to send",{"type":42,"tag":134,"props":189,"children":190},{},[191,193,199,201,207,208],{"type":47,"value":192},"named channel: ",{"type":42,"tag":172,"props":194,"children":196},{"className":195},[],[197],{"type":47,"value":198},"resolve_team",{"type":47,"value":200},", ",{"type":42,"tag":172,"props":202,"children":204},{"className":203},[],[205],{"type":47,"value":206},"resolve_channel",{"type":47,"value":179},{"type":42,"tag":172,"props":209,"children":211},{"className":210},[],[212],{"type":47,"value":213},"list_channel_messages",{"type":42,"tag":134,"props":215,"children":216},{},[217,219,225,226],{"type":47,"value":218},"named chat or DM: ",{"type":42,"tag":172,"props":220,"children":222},{"className":221},[],[223],{"type":47,"value":224},"resolve_chat",{"type":47,"value":179},{"type":42,"tag":172,"props":227,"children":229},{"className":228},[],[230],{"type":47,"value":231},"list_chat_messages",{"type":42,"tag":134,"props":233,"children":234},{},[235,237],{"type":47,"value":236},"If no explicit scope was provided, start with:\n",{"type":42,"tag":130,"props":238,"children":239},{},[240,251],{"type":42,"tag":134,"props":241,"children":242},{},[243,249],{"type":42,"tag":172,"props":244,"children":246},{"className":245},[],[247],{"type":47,"value":248},"list_chats(unread_only=True)",{"type":47,"value":250}," for unread direct conversations and group chats",{"type":42,"tag":134,"props":252,"children":253},{},[254,260],{"type":42,"tag":172,"props":255,"children":257},{"className":256},[],[258],{"type":47,"value":259},"list_recent_threads",{"type":47,"value":261}," for recent channel or chat activity",{"type":42,"tag":134,"props":263,"children":264},{},[265,267],{"type":47,"value":266},"Expand only the conversations needed to answer accurately:\n",{"type":42,"tag":130,"props":268,"children":269},{},[270,275,280],{"type":42,"tag":134,"props":271,"children":272},{},[273],{"type":47,"value":274},"unread chats first",{"type":42,"tag":134,"props":276,"children":277},{},[278],{"type":47,"value":279},"then recent messages containing direct questions or clear asks",{"type":42,"tag":134,"props":281,"children":282},{},[283],{"type":47,"value":284},"then recent mentions detected from message-history reads",{"type":42,"tag":134,"props":286,"children":287},{},[288,290,296],{"type":47,"value":289},"To detect recent mentions, get the caller profile and match ",{"type":42,"tag":172,"props":291,"children":293},{"className":292},[],[294],{"type":47,"value":295},"TeamsMessageResult.mentions",{"type":47,"value":297}," against the caller's user ID from direct message-history reads. Do not rely on Teams search hits for mention detection.",{"type":42,"tag":134,"props":299,"children":300},{},[301],{"type":47,"value":302},"If the context is incomplete, write the smallest useful clarifying reply instead of guessing.",{"type":42,"tag":134,"props":304,"children":305},{},[306],{"type":47,"value":307},"If a message contains a follow-up but no reply is needed, say that directly. If the user wants it tracked, route the follow-up to the Planner skill instead of drafting a performative Teams reply.",{"type":42,"tag":56,"props":309,"children":311},{"id":310},"drafting-rules",[312],{"type":47,"value":313},"Drafting Rules",{"type":42,"tag":130,"props":315,"children":316},{},[317,322,327,332],{"type":42,"tag":134,"props":318,"children":319},{},[320],{"type":47,"value":321},"Answer the question first, then add clarification or next steps only when the context supports it.",{"type":42,"tag":134,"props":323,"children":324},{},[325],{"type":47,"value":326},"Keep in-thread replies short unless the thread clearly requires a longer answer.",{"type":42,"tag":134,"props":328,"children":329},{},[330],{"type":47,"value":331},"Preserve thread-specific facts, dates, links, and owners.",{"type":42,"tag":134,"props":333,"children":334},{},[335],{"type":47,"value":336},"If there are multiple plausible reply targets, stop and ask which conversation the user means before drafting anything send-ready.",{"type":42,"tag":56,"props":338,"children":340},{"id":339},"formatting",[341],{"type":47,"value":342},"Formatting",{"type":42,"tag":50,"props":344,"children":345},{},[346],{"type":47,"value":347},"Format multiple drafts as:",{"type":42,"tag":349,"props":350,"children":355},"pre",{"className":351,"code":352,"language":353,"meta":354,"style":354},"language-md shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","*Teams Reply Drafts — \u003Cscope>*\n\n*\u003Cchat \u002F channel \u002F thread info>*\nDraft:\n\u003Cdraft text>\n\n*\u003Cchat \u002F channel \u002F thread info>*\nDraft:\n\u003Cdraft text>\n","md","",[356],{"type":42,"tag":172,"props":357,"children":358},{"__ignoreMap":354},[359,382,392,409,419,428,436,452,460],{"type":42,"tag":360,"props":361,"children":364},"span",{"class":362,"line":363},"line",1,[365,371,377],{"type":42,"tag":360,"props":366,"children":368},{"style":367},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[369],{"type":47,"value":370},"*",{"type":42,"tag":360,"props":372,"children":374},{"style":373},"--shiki-light:#E53935;--shiki-light-font-style:italic;--shiki-default:#F07178;--shiki-default-font-style:italic;--shiki-dark:#F07178;--shiki-dark-font-style:italic",[375],{"type":47,"value":376},"Teams Reply Drafts — \u003Cscope>",{"type":42,"tag":360,"props":378,"children":379},{"style":367},[380],{"type":47,"value":381},"*\n",{"type":42,"tag":360,"props":383,"children":385},{"class":362,"line":384},2,[386],{"type":42,"tag":360,"props":387,"children":389},{"emptyLinePlaceholder":388},true,[390],{"type":47,"value":391},"\n",{"type":42,"tag":360,"props":393,"children":395},{"class":362,"line":394},3,[396,400,405],{"type":42,"tag":360,"props":397,"children":398},{"style":367},[399],{"type":47,"value":370},{"type":42,"tag":360,"props":401,"children":402},{"style":373},[403],{"type":47,"value":404},"\u003Cchat \u002F channel \u002F thread info>",{"type":42,"tag":360,"props":406,"children":407},{"style":367},[408],{"type":47,"value":381},{"type":42,"tag":360,"props":410,"children":412},{"class":362,"line":411},4,[413],{"type":42,"tag":360,"props":414,"children":416},{"style":415},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[417],{"type":47,"value":418},"Draft:\n",{"type":42,"tag":360,"props":420,"children":422},{"class":362,"line":421},5,[423],{"type":42,"tag":360,"props":424,"children":425},{"style":415},[426],{"type":47,"value":427},"\u003Cdraft text>\n",{"type":42,"tag":360,"props":429,"children":431},{"class":362,"line":430},6,[432],{"type":42,"tag":360,"props":433,"children":434},{"emptyLinePlaceholder":388},[435],{"type":47,"value":391},{"type":42,"tag":360,"props":437,"children":439},{"class":362,"line":438},7,[440,444,448],{"type":42,"tag":360,"props":441,"children":442},{"style":367},[443],{"type":47,"value":370},{"type":42,"tag":360,"props":445,"children":446},{"style":373},[447],{"type":47,"value":404},{"type":42,"tag":360,"props":449,"children":450},{"style":367},[451],{"type":47,"value":381},{"type":42,"tag":360,"props":453,"children":455},{"class":362,"line":454},8,[456],{"type":42,"tag":360,"props":457,"children":458},{"style":415},[459],{"type":47,"value":418},{"type":42,"tag":360,"props":461,"children":463},{"class":362,"line":462},9,[464],{"type":42,"tag":360,"props":465,"children":466},{"style":415},[467],{"type":47,"value":427},{"type":42,"tag":130,"props":469,"children":470},{},[471,476,481],{"type":42,"tag":134,"props":472,"children":473},{},[474],{"type":47,"value":475},"Keep each item minimal: a short header plus the draft text.",{"type":42,"tag":134,"props":477,"children":478},{},[479],{"type":47,"value":480},"If the user asked for a single reply, return only that item.",{"type":42,"tag":134,"props":482,"children":483},{},[484],{"type":47,"value":485},"If nothing likely needing a reply is found, say so directly and explain the scope checked.",{"type":42,"tag":487,"props":488,"children":489},"style",{},[490],{"type":47,"value":491},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":493,"total":696},[494,515,538,555,571,590,607,623,639,653,665,680],{"slug":495,"name":495,"fn":496,"description":497,"org":498,"tags":499,"stars":512,"repoUrl":513,"updatedAt":514},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[500,503,506,509],{"name":501,"slug":502,"type":15},"Documents","documents",{"name":504,"slug":505,"type":15},"Healthcare","healthcare",{"name":507,"slug":508,"type":15},"Insurance","insurance",{"name":510,"slug":511,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":516,"name":516,"fn":517,"description":518,"org":519,"tags":520,"stars":535,"repoUrl":536,"updatedAt":537},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[521,524,526,529,532],{"name":522,"slug":523,"type":15},".NET","dotnet",{"name":525,"slug":516,"type":15},"ASP.NET Core",{"name":527,"slug":528,"type":15},"Blazor","blazor",{"name":530,"slug":531,"type":15},"C#","csharp",{"name":533,"slug":534,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":539,"name":539,"fn":540,"description":541,"org":542,"tags":543,"stars":535,"repoUrl":536,"updatedAt":554},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[544,547,550,553],{"name":545,"slug":546,"type":15},"Apps SDK","apps-sdk",{"name":548,"slug":549,"type":15},"ChatGPT","chatgpt",{"name":551,"slug":552,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":556,"name":556,"fn":557,"description":558,"org":559,"tags":560,"stars":535,"repoUrl":536,"updatedAt":570},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[561,564,567],{"name":562,"slug":563,"type":15},"API Development","api-development",{"name":565,"slug":566,"type":15},"CLI","cli",{"name":568,"slug":569,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":572,"name":572,"fn":573,"description":574,"org":575,"tags":576,"stars":535,"repoUrl":536,"updatedAt":589},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[577,580,583,586],{"name":578,"slug":579,"type":15},"Cloudflare","cloudflare",{"name":581,"slug":582,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":584,"slug":585,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":587,"slug":588,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":591,"name":591,"fn":592,"description":593,"org":594,"tags":595,"stars":535,"repoUrl":536,"updatedAt":606},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[596,597,600,603],{"name":13,"slug":14,"type":15},{"name":598,"slug":599,"type":15},"Project Management","project-management",{"name":601,"slug":602,"type":15},"Strategy","strategy",{"name":604,"slug":605,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":608,"name":608,"fn":609,"description":610,"org":611,"tags":612,"stars":535,"repoUrl":536,"updatedAt":622},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[613,616,618,621],{"name":614,"slug":615,"type":15},"Design","design",{"name":617,"slug":608,"type":15},"Figma",{"name":619,"slug":620,"type":15},"Frontend","frontend",{"name":551,"slug":552,"type":15},"2026-04-12T05:06:47.939943",{"slug":624,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":535,"repoUrl":536,"updatedAt":638},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[629,630,633,634,635],{"name":614,"slug":615,"type":15},{"name":631,"slug":632,"type":15},"Design System","design-system",{"name":617,"slug":608,"type":15},{"name":619,"slug":620,"type":15},{"name":636,"slug":637,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":640,"name":640,"fn":641,"description":642,"org":643,"tags":644,"stars":535,"repoUrl":536,"updatedAt":652},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[645,646,647,650,651],{"name":614,"slug":615,"type":15},{"name":631,"slug":632,"type":15},{"name":648,"slug":649,"type":15},"Documentation","documentation",{"name":617,"slug":608,"type":15},{"name":619,"slug":620,"type":15},"2026-05-16T06:07:47.821474",{"slug":654,"name":654,"fn":655,"description":656,"org":657,"tags":658,"stars":535,"repoUrl":536,"updatedAt":664},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[659,660,661,662,663],{"name":614,"slug":615,"type":15},{"name":617,"slug":608,"type":15},{"name":619,"slug":620,"type":15},{"name":636,"slug":637,"type":15},{"name":533,"slug":534,"type":15},"2026-05-16T06:07:40.583615",{"slug":666,"name":666,"fn":667,"description":668,"org":669,"tags":670,"stars":535,"repoUrl":536,"updatedAt":679},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[671,674,675,678],{"name":672,"slug":673,"type":15},"Animation","animation",{"name":568,"slug":569,"type":15},{"name":676,"slug":677,"type":15},"Creative","creative",{"name":614,"slug":615,"type":15},"2026-05-02T05:31:48.48485",{"slug":681,"name":681,"fn":682,"description":683,"org":684,"tags":685,"stars":535,"repoUrl":536,"updatedAt":695},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[686,687,688,691,694],{"name":676,"slug":677,"type":15},{"name":614,"slug":615,"type":15},{"name":689,"slug":690,"type":15},"Image Generation","image-generation",{"name":692,"slug":693,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":698,"total":812},[699,716,732,744,762,780,800],{"slug":700,"name":700,"fn":701,"description":702,"org":703,"tags":704,"stars":25,"repoUrl":26,"updatedAt":715},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[705,708,711,714],{"name":706,"slug":707,"type":15},"Accessibility","accessibility",{"name":709,"slug":710,"type":15},"Charts","charts",{"name":712,"slug":713,"type":15},"Data Visualization","data-visualization",{"name":614,"slug":615,"type":15},"2026-06-30T19:00:57.102",{"slug":717,"name":717,"fn":718,"description":719,"org":720,"tags":721,"stars":25,"repoUrl":26,"updatedAt":731},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[722,725,728],{"name":723,"slug":724,"type":15},"Agents","agents",{"name":726,"slug":727,"type":15},"Browser Automation","browser-automation",{"name":729,"slug":730,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":733,"name":733,"fn":734,"description":735,"org":736,"tags":737,"stars":25,"repoUrl":26,"updatedAt":743},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[738,739,742],{"name":726,"slug":727,"type":15},{"name":740,"slug":741,"type":15},"Local Development","local-development",{"name":729,"slug":730,"type":15},"2026-04-06T18:41:17.526867",{"slug":745,"name":745,"fn":746,"description":747,"org":748,"tags":749,"stars":25,"repoUrl":26,"updatedAt":761},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[750,751,752,755,758],{"name":723,"slug":724,"type":15},{"name":584,"slug":585,"type":15},{"name":753,"slug":754,"type":15},"SDK","sdk",{"name":756,"slug":757,"type":15},"Serverless","serverless",{"name":759,"slug":760,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":763,"name":763,"fn":764,"description":765,"org":766,"tags":767,"stars":25,"repoUrl":26,"updatedAt":779},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[768,769,772,775,776],{"name":619,"slug":620,"type":15},{"name":770,"slug":771,"type":15},"React","react",{"name":773,"slug":774,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":636,"slug":637,"type":15},{"name":777,"slug":778,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":781,"name":781,"fn":782,"description":783,"org":784,"tags":785,"stars":25,"repoUrl":26,"updatedAt":799},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[786,789,792,795,798],{"name":787,"slug":788,"type":15},"AI Infrastructure","ai-infrastructure",{"name":790,"slug":791,"type":15},"Cost Optimization","cost-optimization",{"name":793,"slug":794,"type":15},"LLM","llm",{"name":796,"slug":797,"type":15},"Performance","performance",{"name":777,"slug":778,"type":15},"2026-04-06T18:40:44.377464",{"slug":801,"name":801,"fn":802,"description":803,"org":804,"tags":805,"stars":25,"repoUrl":26,"updatedAt":811},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[806,807,810],{"name":790,"slug":791,"type":15},{"name":808,"slug":809,"type":15},"Database","database",{"name":793,"slug":794,"type":15},"2026-04-06T18:41:08.513425",600]